Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-02 17:22:31 +01:00
Code Issues Releases Activity

[infoq] Use BokeCC extractor function

Browse Source
This commit is contained in:
Yen Chi Hsuan 2016-02-27 02:55:11 +08:00
parent 4435c6e98e
commit 5633b4d39d
1 changed files with 4 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/infoq.py
View File

@ -4,15 +4,12 @@
import base64 import base64
from .common import InfoExtractor from ..compat import compat_urllib_parse_unquote
from ..compat import (
compat_urllib_parse_unquote,
compat_parse_qs,
)
from ..utils import determine_ext from ..utils import determine_ext
from .bokecc import BokeCCBaseIE
class InfoQIE(InfoExtractor): class InfoQIE(BokeCCBaseIE):
_VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)'
_TESTS = [{ _TESTS = [{
@ -38,26 +35,6 @@ class InfoQIE(InfoExtractor):
}, },
}] }]
def _extract_bokecc_videos(self, webpage, video_id):
# TODO: bokecc.com is a Chinese video cloud platform
# It should have an independent extractor but I don't have other
# examples using bokecc
player_params_str = self._html_search_regex(
r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
webpage, 'player params', default=None)
player_params = compat_parse_qs(player_params_str)
info_xml = self._download_xml(
'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
player_params['siteid'][0], player_params['vid'][0]), video_id)
return [{
'format_id': 'bokecc',
'url': quality.find('./copy').attrib['playurl'],
'preference': int(quality.attrib['value']),
} for quality in info_xml.findall('./video/quality')]
def _extract_rtmp_videos(self, webpage): def _extract_rtmp_videos(self, webpage):
# The server URL is hardcoded # The server URL is hardcoded
video_url = 'rtmpe://video.infoq.com/cfx/st/' video_url = 'rtmpe://video.infoq.com/cfx/st/'
@ -101,7 +78,7 @@ def _real_extract(self, url):
if '/cn/' in url: if '/cn/' in url:
# for China videos, HTTP video URL exists but always fails with 403 # for China videos, HTTP video URL exists but always fails with 403
formats = self._extract_bokecc_videos(webpage, video_id) formats = self._extract_bokecc_formats(webpage, video_id)
else: else:
formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage) formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage)